GCVE Workshop - 22 September 2026 (14:00-18:00), Luxembourg Before The Vulnopticon Conference - Registration

CVE-2026-57120 (GCVE-0-2026-57120)

Vulnerability from cvelistv5 – Published: 2026-09-14 14:48 – Updated: 2026-09-16 15:07
VLAI
Title
PraisonAI: execute_code sandbox bypass: str.format C-level attribute access reads every blocklisted dunder
Summary
PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, execute_code sandbox mode permits runtime assembly of blocklisted dunder names and allows str.format or str.format_map to resolve dotted fields through C-level attribute access that bypasses _safe_getattr. This exposes class, qualified-name, base-class, globals, and object-dictionary attributes to prompt-influenced code when approval is automatically granted, producing a high-impact read primitive without establishing a complete in-process execution chain. This issue is fixed in praisonaiagents 1.6.59.
Severity
6.5 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
SSVC
Exploitation: poc Automatable: no Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-09-16 15:06 UTC
CWE
  • CWE-693 - Protection Mechanism Failure
Assigner
References
Impacted products
Vendor Product Version CPE status
MervinPraison praisonaiagents Affected: < 1.6.59
guessed Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-57120",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-09-16T15:06:45.768056Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-09-16T15:07:09.714Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-pv2j-rghr-v5r9"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "praisonaiagents",
          "vendor": "MervinPraison",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 1.6.59"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, execute_code sandbox mode permits runtime assembly of blocklisted dunder names and allows str.format or str.format_map to resolve dotted fields through C-level attribute access that bypasses _safe_getattr. This exposes class, qualified-name, base-class, globals, and object-dictionary attributes to prompt-influenced code when approval is automatically granted, producing a high-impact read primitive without establishing a complete in-process execution chain. This issue is fixed in praisonaiagents 1.6.59."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 6.5,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "NONE",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-693",
              "description": "CWE-693: Protection Mechanism Failure",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-09-14T14:48:14.932Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-pv2j-rghr-v5r9",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-pv2j-rghr-v5r9"
        },
        {
          "name": "https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9"
        },
        {
          "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59"
        }
      ],
      "source": {
        "advisory": "GHSA-pv2j-rghr-v5r9",
        "discovery": "UNKNOWN"
      },
      "title": "PraisonAI: execute_code sandbox bypass: str.format C-level attribute access reads every blocklisted dunder"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-57120",
    "datePublished": "2026-09-14T14:48:14.932Z",
    "dateReserved": "2026-06-24T00:33:17.707Z",
    "dateUpdated": "2026-09-16T15:07:09.714Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-57120",
      "date": "2026-09-17",
      "epss": "0.00318",
      "percentile": "0.24866"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-57120\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-09-14T15:17:05.607\",\"lastModified\":\"2026-09-16T16:17:12.970\",\"vulnStatus\":\"Deferred\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, execute_code sandbox mode permits runtime assembly of blocklisted dunder names and allows str.format or str.format_map to resolve dotted fields through C-level attribute access that bypasses _safe_getattr. This exposes class, qualified-name, base-class, globals, and object-dictionary attributes to prompt-influenced code when approval is automatically granted, producing a high-impact read primitive without establishing a complete in-process execution chain. This issue is fixed in praisonaiagents 1.6.59.\"}],\"affected\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"MervinPraison\",\"product\":\"praisonaiagents\",\"versions\":[{\"version\":\"\u003c 1.6.59\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N\",\"baseScore\":6.5,\"baseSeverity\":\"MEDIUM\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":2.8,\"impactScore\":3.6}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-09-16T15:06:45.768056Z\",\"id\":\"CVE-2026-57120\",\"options\":[{\"exploitation\":\"poc\"},{\"automatable\":\"no\"},{\"technicalImpact\":\"partial\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-693\"}]}],\"references\":[{\"url\":\"https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-pv2j-rghr-v5r9\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-pv2j-rghr-v5r9\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-57120\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-09-16T15:06:45.768056Z\"}}}], \"references\": [{\"url\": \"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-pv2j-rghr-v5r9\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-09-16T15:07:03.406Z\"}}], \"cna\": {\"title\": \"PraisonAI: execute_code sandbox bypass: str.format C-level attribute access reads every blocklisted dunder\", \"source\": {\"advisory\": \"GHSA-pv2j-rghr-v5r9\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 6.5, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"MEDIUM\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N\", \"integrityImpact\": \"NONE\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"LOW\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"MervinPraison\", \"product\": \"praisonaiagents\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 1.6.59\"}]}], \"references\": [{\"url\": \"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-pv2j-rghr-v5r9\", \"name\": \"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-pv2j-rghr-v5r9\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9\", \"name\": \"https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59\", \"name\": \"https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, execute_code sandbox mode permits runtime assembly of blocklisted dunder names and allows str.format or str.format_map to resolve dotted fields through C-level attribute access that bypasses _safe_getattr. This exposes class, qualified-name, base-class, globals, and object-dictionary attributes to prompt-influenced code when approval is automatically granted, producing a high-impact read primitive without establishing a complete in-process execution chain. This issue is fixed in praisonaiagents 1.6.59.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-693\", \"description\": \"CWE-693: Protection Mechanism Failure\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-09-14T14:48:14.932Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-57120\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-09-16T15:07:09.714Z\", \"dateReserved\": \"2026-06-24T00:33:17.707Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-09-14T14:48:14.932Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.


Detection rules are retrieved from Rulezet.


Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.